High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

DeepC-MVS	66.32 2	73.85 23	78.10 22	68.90 23	67.92 50	79.31 11	78.16 29	59.28 1	78.24 22	61.13 20	67.36 36	76.10 33	63.40 8	79.11 8	78.41 10	83.52 5	88.16 12
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HPM-MVS++		76.01 9	80.47 11	70.81 9	76.60 8	74.96 36	80.18 17	58.36 2	81.96 10	63.50 12	78.80 14	82.53 10	64.40 5	78.74 9	78.84 5	81.81 32	87.46 18

SMA-MVS		77.32 6	82.51 6	71.26 7	75.43 14	80.19 8	82.22 7	58.26 3	84.83 6	64.36 8	78.19 15	83.46 5	63.61 7	81.00 1	80.28 1	83.66 4	89.62 5
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
SED-MVS		79.21 1	84.74 2	72.75 1	78.66 3	81.96 2	82.94 5	58.16 4	86.82 2	67.66 1	88.29 4	86.15 2	66.42 1	80.41 3	78.65 6	82.65 17	90.92 2

SteuartSystems-ACMMP		75.23 12	79.60 14	70.13 13	76.81 7	78.92 12	81.74 8	57.99 5	75.30 30	59.83 26	75.69 18	78.45 24	60.48 29	80.58 2	79.77 2	83.94 3	88.52 9
Skip Steuart: Steuart Systems R&D Blog.
DVP-MVS		78.77 2	84.89 1	71.62 4	78.04 4	82.05 1	81.64 10	57.96 6	87.53 1	66.64 2	88.77 1	86.31 1	63.16 9	79.99 6	78.56 7	82.31 22	91.03 1
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
MSP-MVS		77.82 4	83.46 4	71.24 8	75.26 16	80.22 7	82.95 4	57.85 7	85.90 3	64.79 5	88.54 3	83.43 6	66.24 2	78.21 17	78.56 7	80.34 47	89.39 6
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
DPE-MVS		78.11 3	83.84 3	71.42 5	77.82 6	81.32 3	82.92 6	57.81 8	84.04 7	63.19 13	88.63 2	86.00 3	64.52 4	78.71 10	77.63 15	82.26 23	90.57 3
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		77.58 5	82.93 5	71.35 6	77.86 5	80.55 6	83.38 1	57.61 9	85.57 4	61.11 21	86.10 6	82.98 7	64.76 3	78.29 14	76.78 22	83.40 6	90.20 4

xxxxxxxxxxxxxcwj		74.63 16	77.07 27	71.79 2	79.32 1	80.76 4	82.96 2	57.49 10	82.82 8	64.79 5	83.69 9	52.03 120	62.83 13	77.13 26	75.21 31	83.35 7	87.85 15

SF-MVS		77.13 7	81.70 7	71.79 2	79.32 1	80.76 4	82.96 2	57.49 10	82.82 8	64.79 5	83.69 9	84.46 4	62.83 13	77.13 26	75.21 31	83.35 7	87.85 15

APD-MVS		75.80 10	80.90 10	69.86 16	75.42 15	78.48 16	81.43 13	57.44 12	80.45 15	59.32 27	85.28 7	80.82 17	63.96 6	76.89 29	76.08 27	81.58 38	88.30 11
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CNVR-MVS		75.62 11	79.91 13	70.61 10	75.76 10	78.82 14	81.66 9	57.12 13	79.77 17	63.04 14	70.69 24	81.15 15	62.99 10	80.23 4	79.54 3	83.11 9	89.16 7

ACMMP_NAP		76.15 8	81.17 8	70.30 11	74.09 20	79.47 10	81.59 12	57.09 14	81.38 11	63.89 11	79.02 13	80.48 18	62.24 18	80.05 5	79.12 4	82.94 12	88.64 8

NCCC		74.27 19	77.83 24	70.13 13	75.70 11	77.41 23	80.51 15	57.09 14	78.25 21	62.28 18	65.54 37	78.26 25	62.18 19	79.13 7	78.51 9	83.01 11	87.68 17

HFP-MVS		74.87 14	78.86 19	70.21 12	73.99 21	77.91 18	80.36 16	56.63 16	78.41 20	64.27 9	74.54 20	77.75 28	62.96 11	78.70 11	77.82 12	83.02 10	86.91 21

MP-MVS		74.31 18	78.87 17	68.99 22	73.49 23	78.56 15	79.25 23	56.51 17	75.33 28	60.69 23	75.30 19	79.12 23	61.81 21	77.78 21	77.93 11	82.18 28	88.06 13
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
zzz-MVS		74.25 20	77.97 23	69.91 15	73.43 24	74.06 44	79.69 19	56.44 18	80.74 14	64.98 4	68.72 30	79.98 20	62.92 12	78.24 16	77.77 14	81.99 30	86.30 23

ACMMPR		73.79 24	78.41 20	68.40 25	72.35 28	77.79 19	79.32 21	56.38 19	77.67 24	58.30 32	74.16 21	76.66 29	61.40 23	78.32 13	77.80 13	82.68 16	86.51 22

OPM-MVS		69.33 38	71.05 46	67.32 28	72.34 29	75.70 33	79.57 20	56.34 20	55.21 73	53.81 54	59.51 63	68.96 55	59.67 35	77.61 23	76.44 25	82.19 27	83.88 40

train_agg		73.89 22	78.25 21	68.80 24	75.25 17	72.27 52	79.75 18	56.05 21	74.87 33	58.97 28	81.83 11	79.76 21	61.05 26	77.39 25	76.01 28	81.71 35	85.61 30

CP-MVS		72.63 28	76.95 28	67.59 27	70.67 36	75.53 34	77.95 31	56.01 22	75.65 27	58.82 29	69.16 29	76.48 31	60.46 30	77.66 22	77.20 20	81.65 36	86.97 20

X-MVS		71.18 33	75.66 33	65.96 36	71.71 30	76.96 26	77.26 33	55.88 23	72.75 38	54.48 49	64.39 41	74.47 38	54.19 67	77.84 20	77.37 17	82.21 26	85.85 27

TSAR-MVS + MP.		75.22 13	80.06 12	69.56 17	74.61 18	72.74 50	80.59 14	55.70 24	80.80 13	62.65 16	86.25 5	82.92 8	62.07 20	76.89 29	75.66 30	81.77 34	85.19 33
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
EPNet		65.14 57	69.54 54	60.00 58	66.61 56	67.67 74	67.53 64	55.32 25	62.67 60	46.22 80	67.74 33	65.93 66	48.07 110	72.17 57	72.12 50	76.28 91	78.47 67
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SD-MVS		74.43 17	78.87 17	69.26 20	74.39 19	73.70 46	79.06 25	55.24 26	81.04 12	62.71 15	80.18 12	82.61 9	61.70 22	75.43 41	73.92 44	82.44 21	85.22 32
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
DPM-MVS		72.80 27	75.90 30	69.19 21	75.51 13	77.68 20	81.62 11	54.83 27	75.96 26	62.06 19	63.96 43	76.58 30	58.55 40	76.66 33	76.77 23	82.60 19	83.68 42

CDPH-MVS		71.47 32	75.82 32	66.41 32	72.97 26	77.15 25	78.14 30	54.71 28	69.88 48	53.07 56	70.98 23	74.83 37	56.95 52	76.22 34	76.57 24	82.62 18	85.09 34

SR-MVS					71.46 34			54.67 29				81.54 13

PGM-MVS		72.89 26	77.13 26	67.94 26	72.47 27	77.25 24	79.27 22	54.63 30	73.71 35	57.95 34	72.38 22	75.33 35	60.75 27	78.25 15	77.36 18	82.57 20	85.62 29

MCST-MVS		73.67 25	77.39 25	69.33 19	76.26 9	78.19 17	78.77 26	54.54 31	75.33 28	59.99 25	67.96 32	79.23 22	62.43 17	78.00 18	75.71 29	84.02 2	87.30 19

DeepC-MVS_fast	65.08 3	72.00 30	76.11 29	67.21 29	68.93 46	77.46 21	76.54 35	54.35 32	74.92 32	58.64 31	65.18 38	74.04 43	62.62 15	77.92 19	77.02 21	82.16 29	86.21 24
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMM	60.30 7	67.58 48	68.82 58	66.13 34	70.59 37	72.01 54	76.54 35	54.26 33	65.64 54	54.78 47	50.35 105	61.72 80	58.74 38	75.79 39	75.03 34	81.88 31	81.17 52
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DeepPCF-MVS	66.49 1	74.25 20	80.97 9	66.41 32	67.75 52	78.87 13	75.61 39	54.16 34	84.86 5	58.22 33	77.94 16	81.01 16	62.52 16	78.34 12	77.38 16	80.16 50	88.40 10

ACMMP		71.57 31	75.84 31	66.59 31	70.30 40	76.85 29	78.46 28	53.95 35	73.52 36	55.56 39	70.13 26	71.36 48	58.55 40	77.00 28	76.23 26	82.71 15	85.81 28
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
LGP-MVS_train		68.87 40	72.03 42	65.18 40	69.33 44	74.03 45	76.67 34	53.88 36	68.46 49	52.05 60	63.21 46	63.89 69	56.31 56	75.99 37	74.43 40	82.83 14	84.18 36

AdaColmap		67.89 46	68.85 57	66.77 30	73.73 22	74.30 43	75.28 40	53.58 37	70.24 46	57.59 35	51.19 102	59.19 91	60.74 28	75.33 43	73.72 46	79.69 55	77.96 70

ACMP	61.42 5	68.72 43	71.37 44	65.64 38	69.06 45	74.45 42	75.88 38	53.30 38	68.10 50	55.74 38	61.53 58	62.29 76	56.97 51	74.70 45	74.23 42	82.88 13	84.31 35
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
HQP-MVS		70.88 34	75.02 34	66.05 35	71.69 31	74.47 41	77.51 32	53.17 39	72.89 37	54.88 45	70.03 27	70.48 50	57.26 48	76.02 36	75.01 36	81.78 33	86.21 24

TranMVSNet+NR-MVSNet		55.87 115	60.14 105	50.88 119	59.46 95	63.82 111	57.93 125	52.98 40	48.94 111	20.52 185	52.87 90	47.33 144	36.81 164	69.12 83	69.03 72	77.56 75	69.89 122

UniMVSNet_NR-MVSNet		56.94 108	61.14 91	52.05 117	60.02 92	65.21 104	57.44 127	52.93 41	49.37 105	24.31 178	54.62 86	50.54 127	39.04 150	68.69 85	68.84 74	78.53 65	70.72 116

CSCG		74.68 15	79.22 15	69.40 18	75.69 12	80.01 9	79.12 24	52.83 42	79.34 18	63.99 10	70.49 25	82.02 11	60.35 31	77.48 24	77.22 19	84.38 1	87.97 14

3Dnovator+	62.63 4	69.51 36	72.62 40	65.88 37	68.21 49	76.47 30	73.50 49	52.74 43	70.85 44	58.65 30	55.97 76	69.95 51	61.11 25	76.80 31	75.09 33	81.09 43	83.23 45

CPTT-MVS		68.76 42	73.01 38	63.81 48	65.42 62	73.66 47	76.39 37	52.08 44	72.61 39	50.33 63	60.73 59	72.65 46	59.43 37	73.32 53	72.12 50	79.19 60	85.99 26

Baseline_NR-MVSNet		53.50 132	57.89 129	48.37 144	54.60 134	59.25 145	56.10 137	51.84 45	49.32 106	17.92 192	45.38 142	47.68 139	36.93 163	68.11 98	65.95 115	72.84 131	69.57 127

DU-MVS		55.41 120	59.59 111	50.54 122	54.60 134	62.97 115	57.44 127	51.80 46	48.62 119	24.31 178	51.99 97	47.00 147	39.04 150	68.11 98	67.75 87	76.03 98	70.72 116

NR-MVSNet		55.35 121	59.46 115	50.56 121	61.33 84	62.97 115	57.91 126	51.80 46	48.62 119	20.59 184	51.99 97	44.73 172	34.10 174	68.58 88	68.64 76	77.66 71	70.67 120

MVS_111021_HR		67.62 47	70.39 50	64.39 44	69.77 42	70.45 58	71.44 55	51.72 48	60.77 64	55.06 43	62.14 55	66.40 65	58.13 43	76.13 35	74.79 38	80.19 49	82.04 49

DTE-MVSNet		48.03 171	53.28 158	41.91 178	54.64 132	57.50 161	44.63 194	51.66 49	41.02 174	7.97 212	46.26 131	40.90 185	20.24 198	60.45 162	62.89 149	72.33 143	63.97 164

PEN-MVS		49.21 161	54.32 151	43.24 174	54.33 137	59.26 144	47.04 181	51.37 50	41.67 170	9.97 206	46.22 132	41.80 183	22.97 196	60.52 161	64.03 138	73.73 118	66.75 143

ACMH+	53.71 12	59.26 82	60.28 100	58.06 70	64.17 70	68.46 65	67.51 65	50.93 51	52.46 90	35.83 132	40.83 172	45.12 166	52.32 87	69.88 77	69.00 73	77.59 74	76.21 87

TSAR-MVS + GP.		69.71 35	73.92 37	64.80 43	68.27 48	70.56 57	71.90 51	50.75 52	71.38 42	57.46 36	68.68 31	75.42 34	60.10 33	73.47 52	73.99 43	80.32 48	83.97 38

UniMVSNet (Re)		55.15 125	60.39 99	49.03 134	55.31 128	64.59 108	55.77 142	50.63 53	48.66 118	20.95 183	51.47 100	50.40 128	34.41 173	67.81 105	67.89 83	77.11 82	71.88 110

CP-MVSNet		48.37 166	53.53 155	42.34 176	51.35 159	58.01 158	46.56 182	50.54 54	41.62 171	10.61 202	46.53 130	40.68 188	23.18 194	58.71 171	61.83 155	71.81 146	67.36 142

PS-CasMVS		48.18 168	53.25 159	42.27 177	51.26 160	57.94 159	46.51 183	50.52 55	41.30 172	10.56 203	45.35 144	40.34 190	23.04 195	58.66 172	61.79 156	71.74 148	67.38 141

MAR-MVS		68.04 45	70.74 48	64.90 42	71.68 32	76.33 31	74.63 44	50.48 56	63.81 56	55.52 40	54.88 82	69.90 52	57.39 47	75.42 42	74.79 38	79.71 52	80.03 57
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
abl_6				64.36 45	70.08 41	77.45 22	72.88 50	50.15 57	71.31 43	54.77 48	62.79 50	77.99 27	56.80 53			81.50 39	83.91 39

WR-MVS		48.78 165	55.06 147	41.45 180	55.50 127	60.40 134	43.77 195	49.99 58	41.92 168	8.10 211	45.24 145	45.56 160	17.47 200	61.57 158	64.60 132	73.85 116	66.14 151

PCF-MVS	59.98 8	67.32 49	71.04 47	62.97 50	64.77 64	74.49 40	74.78 43	49.54 59	67.44 51	54.39 52	58.35 68	72.81 45	55.79 63	71.54 60	69.24 69	78.57 63	83.41 43
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WR-MVS_H		47.65 172	53.67 154	40.63 183	51.45 157	59.74 141	44.71 193	49.37 60	40.69 176	7.61 213	46.04 135	44.34 177	17.32 201	57.79 177	61.18 158	73.30 127	65.86 153

PHI-MVS		69.27 39	74.84 35	62.76 51	66.83 54	74.83 37	73.88 47	49.32 61	70.61 45	50.93 61	69.62 28	74.84 36	57.25 49	75.53 40	74.32 41	78.35 68	84.17 37

ACMH	52.42 13	58.24 97	59.56 114	56.70 86	66.34 58	69.59 60	66.71 73	49.12 62	46.08 137	28.90 160	42.67 167	41.20 184	52.60 84	71.39 61	70.28 62	76.51 87	75.72 90
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PVSNet_Blended_VisFu		63.65 60	66.92 61	59.83 61	60.03 91	73.44 48	66.33 76	48.95 63	52.20 91	50.81 62	56.07 75	60.25 87	53.56 73	73.23 54	70.01 65	79.30 57	83.24 44

LS3D		60.20 79	61.70 88	58.45 68	64.18 69	67.77 71	67.19 66	48.84 64	61.67 62	41.27 106	45.89 137	51.81 121	54.18 68	68.78 84	66.50 108	75.03 107	69.48 129

TSAR-MVS + ACMM		72.56 29	79.07 16	64.96 41	73.24 25	73.16 49	78.50 27	48.80 65	79.34 18	55.32 41	85.04 8	81.49 14	58.57 39	75.06 44	73.75 45	75.35 105	85.61 30

CANet		68.77 41	73.01 38	63.83 47	68.30 47	75.19 35	73.73 48	47.90 66	63.86 55	54.84 46	67.51 34	74.36 41	57.62 44	74.22 48	73.57 48	80.56 45	82.36 46

MVS_0304		69.49 37	73.96 36	64.28 46	67.92 50	76.13 32	74.90 42	47.60 67	63.29 58	54.09 53	67.44 35	76.35 32	59.53 36	75.81 38	75.03 34	81.62 37	83.70 41

Anonymous202405211			60.60 96		63.44 75	66.71 90	61.00 111	47.23 68	50.62 97		36.85 182	60.63 86	43.03 136	69.17 81	67.72 88	75.41 102	72.54 108

QAPM		65.27 54	69.49 55	60.35 56	65.43 61	72.20 53	65.69 85	47.23 68	63.46 57	49.14 68	53.56 88	71.04 49	57.01 50	72.60 56	71.41 53	77.62 72	82.14 48

UniMVSNet_ETH3D		52.62 136	55.98 140	48.70 139	51.04 163	60.71 133	56.87 133	46.74 70	42.52 166	26.96 169	42.50 168	45.95 159	37.87 157	66.22 131	65.15 130	72.74 133	68.78 136

FC-MVSNet-train		58.40 93	63.15 85	52.85 111	64.29 67	61.84 121	55.98 141	46.47 71	53.06 83	34.96 135	61.95 57	56.37 104	39.49 148	68.67 86	68.36 79	75.92 99	71.81 111

CDS-MVSNet		52.42 138	57.06 137	47.02 155	53.92 141	58.30 154	55.50 145	46.47 71	42.52 166	29.38 158	49.50 108	52.85 117	28.49 186	66.70 124	66.89 98	68.34 161	62.63 171
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PVSNet_BlendedMVS		61.63 72	64.82 75	57.91 75	57.21 118	67.55 77	63.47 101	46.08 73	54.72 74	52.46 57	58.59 66	60.73 83	51.82 92	70.46 70	65.20 127	76.44 88	76.50 84

PVSNet_Blended		61.63 72	64.82 75	57.91 75	57.21 118	67.55 77	63.47 101	46.08 73	54.72 74	52.46 57	58.59 66	60.73 83	51.82 92	70.46 70	65.20 127	76.44 88	76.50 84

MSLP-MVS++		68.17 44	70.72 49	65.19 39	69.41 43	70.64 56	74.99 41	45.76 75	70.20 47	60.17 24	56.42 74	73.01 44	61.14 24	72.80 55	70.54 60	79.70 53	81.42 51

3Dnovator	60.86 6	66.99 51	70.32 51	63.11 49	66.63 55	74.52 39	71.56 54	45.76 75	67.37 52	55.00 44	54.31 87	68.19 59	58.49 42	73.97 50	73.63 47	81.22 42	80.23 56

Effi-MVS+		63.28 61	65.96 68	60.17 57	64.26 68	68.06 69	68.78 59	45.71 77	54.08 76	46.64 77	55.92 77	63.13 73	55.94 61	70.38 73	71.43 52	79.68 56	78.70 64

UA-Net		58.50 90	64.68 78	51.30 118	66.97 53	67.13 83	53.68 157	45.65 78	49.51 104	31.58 147	62.91 49	68.47 57	35.85 167	68.20 96	67.28 93	74.03 115	69.24 133

DELS-MVS		65.87 52	70.30 52	60.71 54	64.05 72	72.68 51	70.90 56	45.43 79	57.49 68	49.05 70	64.43 40	68.66 56	55.11 65	74.31 46	73.02 49	79.70 53	81.51 50
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
IS_MVSNet		57.95 100	64.26 80	50.60 120	61.62 83	65.25 103	57.18 129	45.42 80	50.79 95	26.49 171	57.81 70	60.05 88	34.51 171	71.24 66	70.20 64	78.36 67	74.44 99

test_part1		63.06 63	65.27 72	60.47 55	66.24 60	70.17 59	71.86 52	45.36 81	53.75 77	49.61 65	44.85 147	65.53 67	48.93 101	71.39 61	70.65 58	80.82 44	80.59 54

Vis-MVSNet (Re-imp)		50.37 153	57.73 133	41.80 179	57.53 107	54.35 169	45.70 187	45.24 82	49.80 100	13.43 198	58.23 69	56.42 102	20.11 199	62.96 150	63.36 144	68.76 160	58.96 184

TransMVSNet (Re)		51.92 145	55.38 144	47.88 150	60.95 87	59.90 139	53.95 154	45.14 83	39.47 183	24.85 175	43.87 153	46.51 153	29.15 183	67.55 110	65.23 126	73.26 128	65.16 159

v144192		58.23 98	59.40 116	56.87 83	57.56 105	66.89 85	65.70 83	45.01 84	44.06 151	42.88 95	46.61 126	48.09 134	53.49 77	66.94 122	65.90 117	76.61 85	77.29 73

baseline1		54.48 129	58.69 121	49.57 126	60.63 89	58.29 155	55.70 143	44.95 85	49.20 107	29.62 156	54.77 83	54.75 110	35.29 168	67.15 118	64.08 137	71.21 151	62.58 172

v1192		58.51 89	59.66 110	57.17 80	57.82 104	67.72 72	66.21 78	44.83 86	44.15 150	43.49 93	46.68 124	47.94 135	53.55 74	67.39 113	66.51 107	77.13 81	77.20 75

EPP-MVSNet		59.39 81	65.45 71	52.32 115	60.96 86	67.70 73	58.42 123	44.75 87	49.71 101	27.23 168	59.03 64	62.20 77	43.34 132	70.71 69	69.13 71	79.25 59	79.63 59

v1921920		57.89 101	59.02 119	56.58 87	57.55 106	66.66 91	64.72 94	44.70 88	43.55 154	42.73 96	46.17 134	46.93 148	53.51 75	66.78 123	65.75 119	76.29 90	77.28 74

ETV-MVS		63.23 62	66.08 67	59.91 60	63.13 76	68.13 68	67.62 63	44.62 89	53.39 80	46.23 79	58.74 65	58.19 94	57.45 46	73.60 51	71.38 54	80.39 46	79.13 61

v1240		57.55 103	58.63 123	56.29 88	57.30 116	66.48 92	63.77 99	44.56 90	42.77 164	42.48 98	45.64 140	46.28 155	53.46 78	66.32 129	65.80 118	76.16 94	77.13 76

v1144		58.88 85	60.16 104	57.39 79	58.03 102	67.26 80	67.14 68	44.46 91	45.17 142	44.33 90	47.81 119	49.92 131	53.20 82	67.77 106	66.62 105	77.15 80	76.58 81

casdiffmvs		64.09 59	68.13 60	59.37 64	61.81 80	68.32 67	68.48 60	44.45 92	61.95 61	49.12 69	63.04 48	69.67 53	53.83 71	70.46 70	66.06 113	78.55 64	77.43 72

GeoE		62.43 68	64.79 77	59.68 62	64.15 71	67.17 82	68.80 58	44.42 93	55.65 72	47.38 72	51.54 99	62.51 74	54.04 70	69.99 76	68.07 81	79.28 58	78.57 65

DI_MVS_plusplus_trai		61.88 70	65.17 74	58.06 70	60.05 90	65.26 101	66.03 79	44.22 94	55.75 71	46.73 75	54.64 85	68.12 60	54.13 69	69.13 82	66.66 102	77.18 79	76.61 80

v10		59.17 84	60.60 96	57.50 78	57.95 103	66.73 87	67.09 71	44.11 95	46.85 130	45.42 83	48.18 118	51.07 123	53.63 72	67.84 104	66.59 106	76.79 83	76.92 77

pmmvs4		54.66 128	56.07 139	53.00 109	54.63 133	57.08 163	60.43 114	44.10 96	51.69 93	40.55 110	46.55 129	44.79 171	45.95 120	62.54 152	63.66 141	72.36 142	66.20 149

FMVSNet2		55.04 126	59.95 108	49.31 128	52.42 149	61.44 123	57.03 130	44.08 97	49.55 102	30.40 152	46.89 123	58.84 92	38.22 153	67.07 120	66.21 111	73.69 119	69.65 124

GBi-Net		55.20 122	60.25 101	49.31 128	52.42 149	61.44 123	57.03 130	44.04 98	49.18 108	30.47 149	48.28 114	58.19 94	38.22 153	68.05 101	66.96 95	73.69 119	69.65 124

test1		55.20 122	60.25 101	49.31 128	52.42 149	61.44 123	57.03 130	44.04 98	49.18 108	30.47 149	48.28 114	58.19 94	38.22 153	68.05 101	66.96 95	73.69 119	69.65 124

FMVSNet3		54.78 127	59.58 113	49.17 131	52.37 152	61.31 127	56.72 135	44.04 98	49.18 108	30.47 149	48.28 114	58.19 94	38.09 156	65.48 140	65.20 127	73.31 126	69.45 132

tfpnnormal		50.16 155	52.19 167	47.78 152	56.86 121	58.37 153	54.15 153	44.01 101	38.35 191	25.94 172	36.10 183	37.89 197	34.50 172	65.93 134	63.42 143	71.26 150	65.28 157

FMVSNet1		54.08 130	58.68 122	48.71 138	50.90 165	61.35 126	56.73 134	43.94 102	45.91 138	29.32 159	42.72 166	56.26 105	37.70 158	68.05 101	66.96 95	73.69 119	69.50 128

ET-MVSNet_ETH3D		58.38 94	61.57 89	54.67 96	42.15 196	65.26 101	65.70 83	43.82 103	48.84 112	42.34 99	59.76 62	47.76 138	56.68 54	67.02 121	68.60 78	77.33 78	73.73 106

DCV-MVSNet		59.49 80	64.00 81	54.23 97	61.81 80	64.33 109	61.42 107	43.77 104	52.85 87	38.94 120	55.62 79	62.15 78	43.24 135	69.39 80	67.66 89	76.22 93	75.97 88

tfpn200view9		52.53 137	55.51 142	49.06 133	57.31 114	60.24 135	55.42 147	43.77 104	42.85 162	27.81 164	43.00 164	45.06 168	37.32 160	66.38 126	64.54 133	72.71 135	66.54 144

thres600view7		51.91 146	55.14 146	48.14 146	57.43 110	60.18 136	54.60 152	43.73 106	42.61 165	25.20 174	43.10 163	44.47 175	35.19 169	66.36 127	63.28 145	72.66 137	66.01 152

thres200		52.39 139	55.37 145	48.90 135	57.39 111	60.18 136	55.60 144	43.73 106	42.93 160	27.41 166	43.35 159	45.09 167	36.61 165	66.36 127	63.92 140	72.66 137	65.78 154

Anonymous20231211		57.71 102	60.79 94	54.13 99	61.68 82	65.81 97	60.81 112	43.70 108	51.97 92	39.67 115	34.82 187	63.59 70	43.31 133	68.55 90	66.63 104	75.59 100	74.13 102

IterMVS-LS		58.30 96	61.39 90	54.71 95	59.92 93	58.40 152	59.42 117	43.64 109	48.71 116	40.25 113	57.53 71	58.55 93	52.15 89	65.42 142	65.34 123	72.85 130	75.77 89
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EG-PatchMatch MVS		56.98 106	58.24 127	55.50 92	64.66 65	68.62 64	61.48 106	43.63 110	38.44 189	41.44 103	38.05 179	46.18 157	43.95 128	71.71 59	70.61 59	77.87 69	74.08 103

MVS_111021_LR		63.05 64	66.43 64	59.10 65	61.33 84	63.77 112	65.87 82	43.58 111	60.20 65	53.70 55	62.09 56	62.38 75	55.84 62	70.24 74	68.08 80	74.30 112	78.28 69

thres400		52.38 140	55.51 142	48.74 137	57.49 109	60.10 138	55.45 146	43.54 112	42.90 161	26.72 170	43.34 160	45.03 170	36.61 165	66.20 132	64.53 134	72.66 137	66.43 145

v2v482		58.69 88	60.12 107	57.03 81	57.16 120	66.05 94	67.17 67	43.52 113	46.33 134	45.19 86	49.46 109	51.02 124	52.51 85	67.30 114	66.03 114	76.61 85	74.62 98

LTVRE_ROB	44.17 16	47.06 177	50.15 180	43.44 171	51.39 158	58.42 151	42.90 197	43.51 114	22.27 213	14.85 196	41.94 171	34.57 203	45.43 121	62.28 155	62.77 151	62.56 183	68.83 135
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
test20.03		40.38 197	44.20 197	35.92 196	53.73 142	49.05 185	38.54 204	43.49 115	32.55 202	9.54 207	27.88 202	39.12 193	12.24 207	56.28 186	54.69 185	57.96 193	49.83 203

test-LLR		49.28 159	50.29 177	48.10 147	55.26 129	47.16 192	49.52 168	43.48 116	39.22 184	31.98 143	43.65 156	47.93 136	41.29 143	56.80 181	55.36 180	67.08 167	61.94 173

test0.0.03 1		43.15 188	46.95 190	38.72 188	55.26 129	50.56 181	42.48 198	43.48 116	38.16 193	15.11 194	35.07 186	44.69 173	16.47 202	55.95 189	54.34 188	59.54 188	49.87 202

pmmvs-eth3d		51.33 147	52.25 166	50.26 124	50.82 166	54.65 168	56.03 139	43.45 118	43.51 155	37.20 129	39.20 176	39.04 194	42.28 138	61.85 157	62.78 150	71.78 147	64.72 161

Vis-MVSNet		58.48 91	65.70 70	50.06 125	53.40 143	67.20 81	60.24 115	43.32 119	48.83 113	30.23 153	62.38 54	61.61 81	40.35 146	71.03 67	69.77 66	72.82 132	79.11 62
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
UGNet		57.03 105	65.25 73	47.44 153	46.54 182	66.73 87	56.30 136	43.28 120	50.06 98	32.99 139	62.57 53	63.26 72	33.31 176	68.25 93	67.58 90	72.20 144	78.29 68
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
v7n		55.67 117	57.46 135	53.59 103	56.06 124	65.29 100	61.06 110	43.26 121	40.17 180	37.99 124	40.79 173	45.27 165	47.09 114	67.67 108	66.21 111	76.08 96	76.82 78

canonicalmvs		65.62 53	72.06 41	58.11 69	63.94 73	71.05 55	64.49 95	43.18 122	74.08 34	47.35 73	64.17 42	71.97 47	51.17 94	71.87 58	70.74 57	78.51 66	80.56 55

IB-MVS	54.11 11	58.36 95	60.70 95	55.62 91	58.67 98	68.02 70	61.56 104	43.15 123	46.09 136	44.06 91	44.24 150	50.99 126	48.71 104	66.70 124	70.33 61	77.60 73	78.50 66
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
OpenMVS	57.13 9	62.81 65	65.75 69	59.39 63	66.47 57	69.52 61	64.26 97	43.07 124	61.34 63	50.19 64	47.29 122	64.41 68	54.60 66	70.18 75	68.62 77	77.73 70	78.89 63

thres100view900		52.04 143	54.81 149	48.80 136	57.31 114	59.33 143	55.30 148	42.92 125	42.85 162	27.81 164	43.00 164	45.06 168	36.99 162	64.74 145	63.51 142	72.47 140	65.21 158

v8		58.88 85	60.57 98	56.92 82	57.35 113	65.69 98	66.69 74	42.64 126	47.89 125	45.77 81	49.04 110	52.98 116	52.77 83	67.51 111	65.57 120	76.26 92	75.30 96

pm-mvs1		51.02 149	55.55 141	45.73 159	54.16 138	58.52 150	50.92 164	42.56 127	40.32 178	25.67 173	43.66 155	50.34 129	30.06 181	65.85 136	63.97 139	70.99 153	66.21 148

MSDG		58.46 92	58.97 120	57.85 77	66.27 59	66.23 93	67.72 62	42.33 128	53.43 79	43.68 92	43.39 158	45.35 162	49.75 98	68.66 87	67.77 86	77.38 76	67.96 138

Effi-MVS+-dtu		60.34 78	62.32 87	58.03 72	64.31 66	67.44 79	65.99 80	42.26 129	49.55 102	42.00 102	48.92 112	59.79 89	56.27 57	68.07 100	67.03 94	77.35 77	75.45 94

HyFIR lowres test		56.87 109	58.60 124	54.84 94	56.62 123	69.27 62	64.77 93	42.21 130	45.66 140	37.50 127	33.08 190	57.47 99	53.33 79	65.46 141	67.94 82	74.60 109	71.35 113

pmmvs6		48.35 167	51.64 169	44.51 167	51.92 155	57.94 159	49.44 170	42.17 131	34.45 198	24.62 177	28.87 201	46.90 149	29.07 185	64.60 146	63.08 146	69.83 157	65.68 155

EIA-MVS		61.53 74	63.79 82	58.89 66	63.82 74	67.61 75	65.35 88	42.15 132	49.98 99	45.66 82	57.47 72	56.62 101	56.59 55	70.91 68	69.15 70	79.78 51	74.80 97

MVS_Test		62.40 69	66.23 66	57.94 73	59.77 94	64.77 107	66.50 75	41.76 133	57.26 69	49.33 67	62.68 52	67.47 64	53.50 76	68.57 89	66.25 110	76.77 84	76.58 81

gg-mvs-nofinetune		49.07 163	52.56 163	45.00 164	61.99 79	59.78 140	53.55 159	41.63 134	31.62 205	12.08 200	29.56 199	53.28 115	29.57 182	66.27 130	64.49 135	71.19 152	62.92 168

CHOSEN 1792x2688		55.85 116	58.01 128	53.33 104	57.26 117	62.82 117	63.29 103	41.55 135	46.65 132	38.34 121	34.55 188	53.50 113	52.43 86	67.10 119	67.56 91	67.13 166	73.92 105

MS-PatchMatch		58.19 99	60.20 103	55.85 90	65.17 63	64.16 110	64.82 92	41.48 136	50.95 94	42.17 101	45.38 142	56.42 102	48.08 109	68.30 92	66.70 101	73.39 123	69.46 131

TSAR-MVS + COLMAP		62.65 67	69.90 53	54.19 98	46.31 183	66.73 87	65.49 87	41.36 137	76.57 25	46.31 78	76.80 17	56.68 100	53.27 81	69.50 79	66.65 103	72.40 141	76.36 86

diffmvs		61.64 71	66.55 63	55.90 89	56.63 122	63.71 113	67.13 69	41.27 138	59.49 66	46.70 76	63.93 44	68.01 61	50.46 95	67.30 114	65.51 121	73.24 129	77.87 71

CNLPA		62.78 66	66.31 65	58.65 67	58.47 100	68.41 66	65.98 81	41.22 139	78.02 23	56.04 37	46.65 125	59.50 90	57.50 45	69.67 78	65.27 125	72.70 136	76.67 79

USDC		51.11 148	53.71 153	48.08 148	44.76 188	55.99 166	53.01 161	40.90 140	52.49 89	36.14 131	44.67 148	33.66 205	43.27 134	63.23 148	61.10 159	70.39 156	64.82 160

MDA-MVSNet-bldmvs		41.36 191	43.15 201	39.27 187	28.74 211	52.68 175	44.95 192	40.84 141	32.89 201	18.13 191	31.61 193	22.09 216	38.97 152	50.45 203	56.11 175	64.01 176	56.23 190

EPNet_dtu		52.05 142	58.26 126	44.81 165	54.10 139	50.09 184	52.01 162	40.82 142	53.03 84	27.41 166	54.90 81	57.96 98	26.72 188	62.97 149	62.70 152	67.78 164	66.19 150
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TinyColmap		47.08 175	47.56 189	46.52 156	42.35 195	53.44 172	51.77 163	40.70 143	43.44 156	31.92 145	29.78 198	23.72 215	45.04 125	61.99 156	59.54 167	67.35 165	61.03 176

thisisatest0530		56.68 110	59.68 109	53.19 107	52.97 145	60.96 131	59.41 118	40.51 144	48.26 122	41.06 108	52.67 91	46.30 154	49.78 96	67.66 109	67.83 84	75.39 103	74.07 104

tttt0517		56.53 112	59.59 111	52.95 110	52.66 148	60.99 130	59.21 120	40.51 144	47.89 125	40.40 111	52.50 94	46.04 158	49.78 96	67.75 107	67.83 84	75.15 106	74.17 101

baseline2		55.89 114	57.82 130	53.64 101	57.36 112	61.09 129	59.75 116	40.45 146	47.38 128	41.26 107	51.23 101	46.90 149	48.11 108	65.63 139	64.38 136	74.90 108	68.16 137

FC-MVSNet-test		39.65 198	48.35 186	29.49 203	44.43 189	39.28 209	30.23 212	40.44 147	43.59 153	3.12 219	53.00 89	42.03 181	10.02 215	55.09 192	54.77 184	48.66 207	50.71 197

PLC	52.09 14	59.21 83	62.47 86	55.41 93	53.24 144	64.84 106	64.47 96	40.41 148	65.92 53	44.53 89	46.19 133	55.69 108	55.33 64	68.24 95	65.30 124	74.50 110	71.09 114
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
SixPastTwentyTwo		47.55 174	50.25 179	44.41 168	47.30 180	54.31 170	47.81 176	40.36 149	33.76 199	19.93 187	43.75 154	32.77 207	42.07 139	59.82 164	60.94 160	68.98 158	66.37 147

GA-MVS		55.67 117	58.33 125	52.58 114	55.23 131	63.09 114	61.08 109	40.15 150	42.95 159	37.02 130	52.61 92	47.68 139	47.51 112	65.92 135	65.35 122	74.49 111	70.68 119

thisisatest0515		53.85 131	56.84 138	50.37 123	50.25 169	58.17 156	55.99 140	39.90 151	41.88 169	38.16 123	45.91 136	45.30 163	44.58 126	66.15 133	66.89 98	73.36 125	73.57 107

TDRefinement		49.31 158	52.44 164	45.67 161	30.44 209	59.42 142	59.24 119	39.78 152	48.76 115	31.20 148	35.73 184	29.90 209	42.81 137	64.24 147	62.59 154	70.55 154	66.43 145

CS-MVS-test		64.70 58	68.77 59	59.95 59	62.45 78	67.57 76	67.13 69	39.63 153	57.12 70	49.45 66	63.17 47	67.51 63	59.69 34	74.02 49	71.18 55	81.37 41	80.78 53

CS-MVS		65.17 55	68.96 56	60.75 53	62.97 77	67.13 83	68.08 61	39.49 154	58.10 67	52.28 59	63.25 45	69.60 54	60.23 32	74.25 47	71.03 56	81.45 40	79.32 60

SCA		50.99 150	53.22 160	48.40 143	51.07 162	56.78 164	50.25 166	39.05 155	48.31 121	41.38 104	49.54 107	46.70 152	46.00 119	58.31 173	56.28 173	62.65 181	56.60 189

CLD-MVS		67.02 50	71.57 43	61.71 52	71.01 35	74.81 38	71.62 53	38.91 156	71.86 41	60.70 22	64.97 39	67.88 62	51.88 91	76.77 32	74.98 37	76.11 95	69.75 123
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
dps		50.42 152	51.20 173	49.51 127	55.88 125	56.07 165	53.73 155	38.89 157	43.66 152	40.36 112	45.66 139	37.63 199	45.23 123	59.05 166	56.18 174	62.94 180	60.16 180

CR-MVSNet		50.47 151	52.61 162	47.98 149	49.03 174	52.94 173	48.27 173	38.86 158	44.41 146	39.59 116	44.34 149	44.65 174	46.63 116	58.97 168	60.31 163	65.48 171	62.66 169

Patchmtry						47.61 190	48.27 173	38.86 158		39.59 116

Anonymous20231206		42.28 189	45.89 192	38.07 190	51.96 154	48.98 186	43.66 196	38.81 160	38.74 188	14.32 197	26.74 203	40.90 185	20.94 197	56.64 184	54.67 186	58.71 189	54.59 191

v148		55.58 119	57.61 134	53.20 106	54.59 136	61.86 120	61.18 108	38.70 161	44.30 149	42.25 100	47.53 120	50.24 130	48.73 103	65.15 143	62.61 153	73.79 117	71.61 112

PatchMatch-RL		50.11 156	51.56 170	48.43 142	46.23 184	51.94 177	50.21 167	38.62 162	46.62 133	37.51 126	42.43 169	39.38 192	52.24 88	60.98 160	59.56 166	65.76 170	60.01 182

OMC-MVS		65.16 56	71.35 45	57.94 73	52.95 146	68.82 63	69.00 57	38.28 163	79.89 16	55.20 42	62.76 51	68.31 58	56.14 60	71.30 63	68.70 75	76.06 97	79.67 58

tpm cat1		53.30 134	53.41 156	53.17 108	58.16 101	59.15 146	63.73 100	38.27 164	50.73 96	46.98 74	45.57 141	44.00 178	49.20 100	55.90 190	54.02 189	62.65 181	64.50 163

V42		56.97 107	60.14 105	53.28 105	48.16 175	62.78 118	66.30 77	37.93 165	47.44 127	42.68 97	48.19 117	52.59 118	51.90 90	67.46 112	65.94 116	72.72 134	76.55 83

MVSTER		57.19 104	61.11 92	52.62 113	50.82 166	58.79 148	61.55 105	37.86 166	48.81 114	41.31 105	57.43 73	52.10 119	48.60 105	68.19 97	66.75 100	75.56 101	75.68 93

CVMVSNet		46.38 180	52.01 168	39.81 185	42.40 194	50.26 182	46.15 184	37.68 167	40.03 181	15.09 195	46.56 128	47.56 141	33.72 175	56.50 185	55.65 178	63.80 177	67.53 139

PatchmatchNet		49.92 157	51.29 171	48.32 145	51.83 156	51.86 178	53.38 160	37.63 168	47.90 124	40.83 109	48.54 113	45.30 163	45.19 124	56.86 180	53.99 191	61.08 186	54.57 192
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
Fast-Effi-MVS+		60.36 76	63.35 83	56.87 83	58.70 96	65.86 95	65.08 90	37.11 169	53.00 85	45.36 84	52.12 95	56.07 106	56.27 57	71.28 64	69.42 67	78.71 61	75.69 91

DROMVSNet		60.36 76	63.35 83	56.87 83	58.70 96	65.86 95	65.08 90	37.11 169	53.00 85	45.36 84	52.12 95	56.07 106	56.27 57	71.28 64	69.42 67	78.71 61	75.69 91

CANet_DTU		58.88 85	64.68 78	52.12 116	55.77 126	66.75 86	63.92 98	37.04 171	53.32 81	37.45 128	59.81 61	61.81 79	44.43 127	68.25 93	67.47 92	74.12 114	75.33 95

COLMAP_ROB	46.52 15	51.99 144	54.86 148	48.63 140	49.13 173	61.73 122	60.53 113	36.57 172	53.14 82	32.95 140	37.10 180	38.68 195	40.49 145	65.72 137	63.08 146	72.11 145	64.60 162
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TAPA-MVS	54.74 10	60.85 75	66.61 62	54.12 100	47.38 179	65.33 99	65.35 88	36.51 173	75.16 31	48.82 71	54.70 84	63.51 71	53.31 80	68.36 91	64.97 131	73.37 124	74.27 100
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
new-patchmatchnet		33.24 205	37.20 206	28.62 205	44.32 191	38.26 210	29.68 213	36.05 174	31.97 204	6.33 215	26.59 204	27.33 210	11.12 214	50.08 205	41.05 209	44.23 210	45.15 207

CostFormer		56.57 111	59.13 118	53.60 102	57.52 108	61.12 128	66.94 72	35.95 175	53.44 78	44.68 88	55.87 78	54.44 111	48.21 107	60.37 163	58.33 170	68.27 162	70.33 121

MVS-HIRNet		42.24 190	41.15 203	43.51 170	44.06 192	40.74 204	35.77 208	35.35 176	35.38 197	38.34 121	25.63 205	38.55 196	43.48 131	50.77 201	47.03 204	64.07 175	49.98 200

PatchT		48.08 169	51.03 174	44.64 166	42.96 193	50.12 183	40.36 202	35.09 177	43.17 157	39.59 116	42.00 170	39.96 191	46.63 116	58.97 168	60.31 163	63.21 178	62.66 169

testgi		38.71 199	43.64 199	32.95 200	52.30 153	48.63 188	35.59 209	35.05 178	31.58 206	9.03 210	30.29 195	40.75 187	11.19 213	55.30 191	53.47 194	54.53 200	45.48 206

IterMVS-SCA-FT		52.18 141	57.75 132	45.68 160	51.01 164	62.06 119	55.10 150	34.75 179	44.85 143	32.86 141	51.13 103	51.22 122	48.74 102	62.47 153	61.51 157	51.61 205	71.02 115

baseline		55.19 124	60.88 93	48.55 141	49.87 170	58.10 157	58.70 122	34.75 179	52.82 88	39.48 119	60.18 60	60.86 82	45.41 122	61.05 159	60.74 162	63.10 179	72.41 109

IterMVS		53.45 133	57.12 136	49.17 131	49.23 172	60.93 132	59.05 121	34.63 181	44.53 145	33.22 137	51.09 104	51.01 125	48.38 106	62.43 154	60.79 161	70.54 155	69.05 134
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Gipuma		25.87 207	26.91 210	24.66 207	28.98 210	20.17 215	20.46 214	34.62 182	29.55 207	9.10 208	4.91 218	5.31 222	15.76 204	49.37 207	49.10 201	39.03 211	29.95 211
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MDTV_nov1_ep13		50.32 154	52.43 165	47.86 151	49.87 170	54.70 167	58.10 124	34.29 183	45.59 141	37.71 125	47.44 121	47.42 143	41.86 140	58.07 176	55.21 182	65.34 173	58.56 185

EU-MVSNet		40.63 195	45.65 194	34.78 199	39.11 200	46.94 195	40.02 203	34.03 184	33.50 200	10.37 204	35.57 185	37.80 198	23.65 193	51.90 198	50.21 199	61.49 185	63.62 167

RPMNet		46.41 178	48.72 184	43.72 169	47.77 178	52.94 173	46.02 186	33.92 185	44.41 146	31.82 146	36.89 181	37.42 200	37.41 159	53.88 196	54.02 189	65.37 172	61.47 175

MIMVSNet1		35.51 202	41.41 202	28.63 204	27.53 213	43.36 203	38.09 205	33.82 186	32.01 203	6.77 214	21.63 209	35.43 202	11.97 209	55.05 193	53.99 191	53.59 202	48.36 205

MDTV_nov1_ep13_2view		47.62 173	49.72 182	45.18 163	48.05 176	53.70 171	54.90 151	33.80 187	39.90 182	29.79 155	38.85 177	41.89 182	39.17 149	58.99 167	55.55 179	65.34 173	59.17 183

tpmrst		48.08 169	49.88 181	45.98 157	52.71 147	48.11 189	53.62 158	33.70 188	48.70 117	39.74 114	48.96 111	46.23 156	40.29 147	50.14 204	49.28 200	55.80 195	57.71 187

anonymousdsp		52.84 135	57.78 131	47.06 154	40.24 199	58.95 147	53.70 156	33.54 189	36.51 196	32.69 142	43.88 152	45.40 161	47.97 111	67.17 116	70.28 62	74.22 113	82.29 47

EPMVS		44.66 184	47.86 188	40.92 182	47.97 177	44.70 201	47.58 178	33.27 190	48.11 123	29.58 157	49.65 106	44.38 176	34.65 170	51.71 199	47.90 202	52.49 203	48.57 204

pmnet_mix02		40.48 196	43.80 198	36.61 194	45.79 186	40.45 206	42.12 199	33.18 191	40.30 179	24.11 180	38.76 178	37.11 201	24.30 192	52.97 197	46.66 206	50.17 206	50.33 199

pmmvs5		47.07 176	51.02 175	42.46 175	45.18 187	51.47 179	48.23 175	33.09 192	38.17 192	28.62 162	46.60 127	43.48 179	30.74 179	58.28 174	58.63 169	68.92 159	60.48 178

Fast-Effi-MVS+-dtu		56.30 113	59.29 117	52.82 112	58.64 99	64.89 105	65.56 86	32.89 193	45.80 139	35.04 134	45.89 137	54.14 112	49.41 99	67.16 117	66.45 109	75.37 104	70.69 118

MIMVSNet		43.79 187	48.53 185	38.27 189	41.46 197	48.97 187	50.81 165	32.88 194	44.55 144	22.07 181	32.05 191	47.15 145	24.76 191	58.73 170	56.09 176	57.63 194	52.14 193

ADS-MVSNet		40.67 194	43.38 200	37.50 192	44.36 190	39.79 208	42.09 200	32.67 195	44.34 148	28.87 161	40.76 174	40.37 189	30.22 180	48.34 208	45.87 207	46.81 209	44.21 208

gm-plane-assit		44.74 183	45.95 191	43.33 172	60.88 88	46.79 197	36.97 206	32.24 196	24.15 211	11.79 201	29.26 200	32.97 206	46.64 115	65.09 144	62.95 148	71.45 149	60.42 179

tpm		48.82 164	51.27 172	45.96 158	54.10 139	47.35 191	56.05 138	30.23 197	46.70 131	43.21 94	52.54 93	47.55 142	37.28 161	54.11 195	50.50 198	54.90 198	60.12 181

CMPMVS	37.70 17	49.24 160	52.71 161	45.19 162	45.97 185	51.23 180	47.44 179	29.31 198	43.04 158	44.69 87	34.45 189	48.35 133	43.64 129	62.59 151	59.82 165	60.08 187	69.48 129
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
PM-MVS		44.55 185	48.13 187	40.37 184	32.85 208	46.82 196	46.11 185	29.28 199	40.48 177	29.99 154	39.98 175	34.39 204	41.80 141	56.08 188	53.88 193	62.19 184	65.31 156

FMVSNet5		40.96 192	45.81 193	35.29 198	34.30 203	44.55 202	47.28 180	28.84 200	40.76 175	21.62 182	29.85 197	42.44 180	24.77 190	57.53 178	55.00 183	54.93 197	50.56 198

TAMVS		44.02 186	49.18 183	37.99 191	47.03 181	45.97 198	45.04 190	28.47 201	39.11 186	20.23 186	43.22 162	48.52 132	28.49 186	58.15 175	57.95 172	58.71 189	51.36 195

E-PMN		15.09 210	13.19 214	17.30 209	27.80 212	12.62 218	7.81 219	27.54 202	14.62 217	3.19 217	6.89 215	2.52 225	15.09 205	15.93 214	20.22 213	22.38 214	19.53 214

EMVS		14.49 211	12.45 215	16.87 211	27.02 214	12.56 219	8.13 218	27.19 203	15.05 216	3.14 218	6.69 216	2.67 224	15.08 206	14.60 216	18.05 214	20.67 215	17.56 216

N_pmnet		32.67 206	36.85 207	27.79 206	40.55 198	32.13 211	35.80 207	26.79 204	37.24 195	9.10 208	32.02 192	30.94 208	16.30 203	47.22 209	41.21 208	38.21 212	37.21 209

PMVS	27.84 18	33.81 204	35.28 208	32.09 201	34.13 204	24.81 214	32.51 211	26.48 205	26.41 209	19.37 188	23.76 206	24.02 214	25.18 189	50.78 200	47.24 203	54.89 199	49.95 201
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PMMVS		49.20 162	54.28 152	43.28 173	34.13 204	45.70 199	48.98 171	26.09 206	46.31 135	34.92 136	55.22 80	53.47 114	47.48 113	59.43 165	59.04 168	68.05 163	60.77 177

FPMVS		38.36 200	40.41 204	35.97 195	38.92 201	39.85 207	45.50 188	25.79 207	41.13 173	18.70 189	30.10 196	24.56 213	31.86 178	49.42 206	46.80 205	55.04 196	51.03 196

MVE	12.28 19	13.53 212	15.72 212	10.96 213	7.39 219	15.71 217	6.05 220	23.73 208	10.29 219	3.01 220	5.77 217	3.41 223	11.91 210	20.11 212	29.79 211	13.67 218	24.98 212
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
CHOSEN 280x420		40.80 193	45.05 196	35.84 197	32.95 207	29.57 212	44.98 191	23.71 209	37.54 194	18.42 190	31.36 194	47.07 146	46.41 118	56.71 183	54.65 187	48.55 208	58.47 186

RPSCF		46.41 178	54.42 150	37.06 193	25.70 216	45.14 200	45.39 189	20.81 210	62.79 59	35.10 133	44.92 146	55.60 109	43.56 130	56.12 187	52.45 195	51.80 204	63.91 165

TESTMET0.1,1		46.09 181	50.29 177	41.18 181	36.91 202	47.16 192	49.52 168	20.32 211	39.22 184	31.98 143	43.65 156	47.93 136	41.29 143	56.80 181	55.36 180	67.08 167	61.94 173

test-mter		45.30 182	50.37 176	39.38 186	33.65 206	46.99 194	47.59 177	18.59 212	38.75 187	28.00 163	43.28 161	46.82 151	41.50 142	57.28 179	55.78 177	66.93 169	63.70 166

pmmvs3		35.10 203	38.47 205	31.17 202	26.37 215	40.47 205	34.51 210	18.09 213	24.75 210	16.88 193	23.05 207	26.69 211	32.69 177	50.73 202	51.60 196	58.46 192	51.98 194

PMMVS2		15.84 209	19.68 211	11.35 212	15.74 218	16.95 216	13.31 216	17.64 214	16.08 215	0.36 222	13.12 212	11.47 219	1.69 217	28.82 211	27.24 212	19.38 217	24.09 213

new_pmnet		23.19 208	28.17 209	17.37 208	17.03 217	24.92 213	19.66 215	16.16 215	27.05 208	4.42 216	20.77 210	19.20 217	12.19 208	37.71 210	36.38 210	34.77 213	31.17 210

test_method		12.44 213	14.66 213	9.85 214	1.30 221	3.32 221	13.00 217	3.21 216	22.42 212	10.22 205	14.13 211	25.64 212	11.43 212	19.75 213	11.61 216	19.96 216	5.79 217

DeepMVS_CX						6.95 220	5.98 221	2.25 217	11.73 218	2.07 221	11.85 213	5.43 221	11.75 211	11.40 217		8.10 220	18.38 215

tmp_tt				5.40 215	3.97 220	2.35 222	3.26 222	0.44 218	17.56 214	12.09 199	11.48 214	7.14 220	1.98 216	15.68 215	15.49 215	10.69 219

GG-mvs-BLEND		36.62 201	53.39 157	17.06 210	0.01 222	58.61 149	48.63 172	0.01 219	47.13 129	0.02 223	43.98 151	60.64 85	0.03 218	54.92 194	51.47 197	53.64 201	56.99 188

uanet_test		0.00 216	0.00 218	0.00 216	0.00 223	0.00 223	0.00 225	0.00 220	0.00 222	0.00 224	0.00 221	0.00 226	0.00 221	0.00 219	0.00 219	0.00 221	0.00 220

sosnet-low-res		0.00 216	0.00 218	0.00 216	0.00 223	0.00 223	0.00 225	0.00 220	0.00 222	0.00 224	0.00 221	0.00 226	0.00 221	0.00 219	0.00 219	0.00 221	0.00 220

sosnet		0.00 216	0.00 218	0.00 216	0.00 223	0.00 223	0.00 225	0.00 220	0.00 222	0.00 224	0.00 221	0.00 226	0.00 221	0.00 219	0.00 219	0.00 221	0.00 220

testmvs		0.01 214	0.02 216	0.00 216	0.00 223	0.00 223	0.01 224	0.00 220	0.01 220	0.00 224	0.03 220	0.00 226	0.01 219	0.01 218	0.01 217	0.00 221	0.06 219

test123		0.01 214	0.02 216	0.00 216	0.00 223	0.00 223	0.00 225	0.00 220	0.01 220	0.00 224	0.04 219	0.00 226	0.01 219	0.00 219	0.01 217	0.00 221	0.07 218

RE-MVS-def										33.01 138

9.14												81.81 12

our_test_3					51.15 161	57.31 162	55.12 149

ambc			45.54 195		50.66 168	52.63 176	40.99 201		38.36 190	24.67 176	22.62 208	13.94 218	29.14 184	65.71 138	58.06 171	58.60 191	67.43 140

MTAPA										65.14 3		80.20 19

MTMP										62.63 17		78.04 26

Patchmatch-RL test							1.04 223

XVS					70.49 38	76.96 26	74.36 45			54.48 49		74.47 38				82.24 24

X-MVStestdata					70.49 38	76.96 26	74.36 45			54.48 49		74.47 38				82.24 24

mPP-MVS					71.67 33							74.36 41

NP-MVS									72.00 40

High-resolution multi-view benchmark